2025 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics, Mar. 18, 2025
2025 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr 2025)
Inspired by the recently proposed Kolmogorov–Arnold Networks (KANs), we introduce the KAN-based Option Pricing (KANOP) model to value American-style options, building on the conventional Least Square Monte Carlo (LSMC) algorithm. KANs, which are based on Kolmogorov-Arnold representation theorem, offer a data-efficient alternative to traditional Multi-Layer Perceptrons, requiring fewer hidden layers to achieve a higher level of performance. By leveraging the flexibility of KANs, KANOP provides a data-driven alternative to the traditional set of basis functions used in the LSMC model, allowing the model to adapt to the pricing task and effectively estimate the expected continuation value. Using examples of standard American and Asian-American options, we demonstrate that KANOP produces more reliable option value estimates, both for single-dimensional cases and in more complex scenarios involving multiple input variables. The delta estimated by the KANOP model is also more accurate than that obtained using traditional basis functions, which is crucial for effective option hedging. Graphical illustrations further validate KANOP’s ability to accurately model the expected continuation value for American-style options.
Option Pricing; Least Square Monte Carlo; Kolmogorov–Arnold Networks; Basis Functions; option delta;
arXiv:2410.00419 (doi.org/10.48550/arXiv.2410.00419)
@inproceedings{Handal2025-cifer,
title={{KANOP: A Data-Efficient Option Pricing Model using Kolmogorov–Arnold Networks}},
author={Rushikesh Handal and Kazuki Matoya and Yunzhuo Wang and Masanori Hirano},
booktitle={2025 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics},
publisher={IEEE},
archivePrefix={arXiv},
arxivId={2410.00419},
year={2025}
}